Download presentation
Presentation is loading. Please wait.
1
描述資料: 次數表, 次數分配, 以及 統計圖 第二章
Copyright © 2015 McGraw-Hill Education. All rights reserved. No reproduction or distribution without the prior written consent of McGraw-Hill Education.
2
Learning Objectives LO2-1 將 qualitative variables 整理成次數表(frequency tables)與相對次數表(relative frequency tables). LO2-2 用長條圖 (bar chart) 或圓餅圖 (pie chart)來呈現次數表(frequency table) LO2-3 將 quantitative variables整理成次數分配(frequency distributions) and相對次數分配(relative frequency distributions) LO2-4 用直方圖 (histogram)或次數多邊圖(frequency polygon)來呈現次數分配(frequency distribution) 2-*
3
LO2-1 Summarize qualitative variables with frequency and relative frequency tables.
FREQUENCY TABLE 將類別(屬質)資料(qualitative data)分組成 互斥的(mutually exclusive)以及相互獨立,完全耗盡的組別(collectively exhaustive classes) ,並呈現各組觀察值數量的表格。 . 2-*
4
表2-1之說明 Applewood Auto Group有4個銷售點(分店):Kane Motors, Olean Automotive Inc., Sheffield Motors Inc., Tionesta Ford Lincoln Mercury 他們銷售Kia, Hyundai, BMW, Volvo 的sedans(4門轎車),SUV(休旅車),以及福特與雪佛萊的轎車與貨卡車。 Kathryn Ball負責追蹤分析各類車款的銷售成績與獲利率。
5
表2-1,2-2 之說明 每月作圖、作表分析:現購每輛車的利潤,最高/最低利潤,購買者的特性(年齡、之前在其分店購買的車數、車款)。
表2-1呈現上個月4個分店的個別銷售成績(共賣出180輛車)。 表2-2呈現相對次數,表現出各分店銷售數量占總數量的比例。
6
LO2-2 Display a frequency table using a bar or pie chart.
長條圖 Bar Charts BAR CHART 將屬質資料(qualitative classes)的組別 標示於X軸,將各組別次數標示於Y軸的圖形。各組的次數與長條圖的高度成正比。 2-*
7
表2-3 上個月售出車款的次數表 車款: Sedan (四門轎車) 、 SUV (休旅車) 、 Compact (小型車) 、 Truck (貨卡車) 、 Hybrid (油電混合車) 。
8
LO2-2 圓餅圖 Pie Charts PIE CHART 能呈現各組別的次數占總次數之比例的圖形 2-*
9
LO2-2 範例 SkiLodges.com想測試其網頁是否設計良好,是否容易瀏覽使用? 他們隨機選出200位網路常客,請他們在該網站瀏覽搜尋,然後,請他們給予評分,針對其網站瀏覽的難易程度分為:poor, good, excellent, or awesome。 其評分結果呈現於下表中: 2-*
10
LO2-2 Example Continued What type of measurement scale is used for ease of navigation? O Draw a bar chart for the survey results. Draw a pie chart for the survey results. 2-*
11
LO2-2 Pie Chart Using Excel . 2-*
12
Self-Review問題 2-1:p.24 DeCenzo食品公司出售4種口味的可樂與飲品,他們隨機抽問100位顧客最喜歡哪種飲料,結果如下:
13
Self-Review問題 2-1:p.24 問: (a) 這是屬質還是數量資料?為什麼? (b) 前面的表是何種表格?給了什麼資料?
(c) 請繪製長條圖 (d) 請繪製圓餅圖
14
次數分配 Frequency Distribution
LO2-3 Summarize quantitative variables with frequency and relative frequency distributions. 次數分配 Frequency Distribution FREQUENCY DISTRIBUTION 將數量資料依照互斥(mutually exclusive)與相互獨立且完全耗盡(collectively exhaustive)的原則分成不同的組別(classes) ,並呈現各組別觀察值的數量。 例如: Applewood Auto Group上個月賣車利潤的次數分配表 2-*
15
原始數據 (raw data)/未分組資料(ungrouped data)
次數分配表可將未經處理過的原始數據,整理成有意義,且一目了然、可供進一步分析使用的資料。
16
次數分配 Frequency Distribution
LO2-3 次數分配 Frequency Distribution 組距Class interval: 將下一組的組下限減去本組的組下限,便可得到本組的組距。 組次/各組次數Class frequency: 各組的觀察值數目。 組中點Class midpoint: 各組的組上限與組下限的平均值,為分割各組成兩等分的中間點。 2-*
17
Creating a Frequency Distribution Table – Example
LO2-3 Creating a Frequency Distribution Table – Example Kathryn Ball of the Applewood Auto Group wants to describe the data collected on the profits for the 180 vehicles sold last month at the four Applewood locations. She would like to know: What is the typical profit for the 180 vehicles sold? What is the largest profit on any sale? What is the lowest profit on any sale? What is the typical value of profit or around what value of profit does the data tend to cluster? 2-*
18
Frequency Distribution Table – Example (Continued)
LO2-3 Frequency Distribution Table – Example (Continued) Step 1: Decide on the 組數 k number of classes. A useful recipe to determine the number of classes (k) is the “2 to the k rule,” such that 2k > n. (n:觀察值個數) There were 180 vehicles sold, so n = 180. If we try k = 7, then 27 = 128, somewhat less than 180. Hence, 7 is not enough classes. If we let k = 8, then 28 = 256, which is greater than 180. So the recommended number of classes is 8. Step 2: Determine the 組距 class interval or width. The formula is: i (H-L)/k where i is the class interval, H is the highest observed value, L is the lowest observed value, and k is the number of classes. Round up to some convenient number, such as a multiple of 10 or 100. Use a class width of $400. 2-*
19
Frequency Distribution Table – Example (Continued)
LO2-3 Frequency Distribution Table – Example (Continued) Step 3: Set the individual class limits:組上限與組下限. 2-*
20
設定組上限與組下限之注意事項: 組限不可重疊覆蓋、必須清楚劃分,如: , 表示 [200,400), [400,600) 第一組的組下限必須低於最小觀察值,如:最小值為294,第一組可為[ ) 最後一組的組上限必須高過最大觀察值,如:最大值為3292,最後一組可為[3000,3400)
21
Frequency Distribution Table – Example (Continued)
LO2-3 Frequency Distribution Table – Example (Continued) Step 4: Tally the vehicle profits into the classes. Step 5: Count the number of items in each class. 2-*
22
Ex 2-2: p. 29 MCC公司的11個業務去年第一季的佣金為:$1650, 1475, 1510, 1670, 1595, 1760, 1540, 1495, 1590, 1625, 1510 這些數值又可稱作? 按 , 依此類推分組,作次數分配表,此表右欄為何種資料? 依據此表:其資料集中處?最大值、最小值?一般值?
23
Ex 2-2: p. 29 先將原始數據排序,然後作表。 此處可不排序,可先分組: , , , 計算各組的次數,做成次數分配表。 依據次數分配表:找Mo, Min, Max, mean(此處各項值,皆與原始數據無關)
24
相對組次 Relative Class Frequencies
LO2-3 相對組次 Relative Class Frequencies 組次(Class frequencies) can be converted to 相對組次(relative class frequencies) to show the fraction of the total number of observations in each class. A relative frequency captures the relationship between a class total and the total number of observations. 2-*
25
相對次數分配 Relative Frequency Distribution
LO2-3 相對次數分配 Relative Frequency Distribution To convert a 次數分配 (frequency distribution) to a 相對次數分配 (relative frequency distribution), each of the組次(class frequencies) is divided by the total number of observations. 2-*
26
Ex 2-3 (p ) 舊金山巨人隊的Barry Bonds在2001年擊出大聯盟單季最多全壘打紀錄:共73支,下面列出各支全壘打的距離:
27
Ex 2-3 (p ) 該分幾組?組距=?若第一組下限為300,做次數分配表與相對次數分配表。距離介於 之間的全壘打有幾支?佔多少比例?距離超過390的比例為多少?
28
Displays of Frequency Distributions
LO2-4 Display a frequency distribution using a histogram or frequency polygon. Displays of Frequency Distributions The three commonly used graphic forms are: Histograms(直方圖) Frequency polygons(次數多邊圖) Cumulative frequency distributions (累積次數分配) 2-*
29
LO2-4 直方圖 Histogram HISTOGRAM 將各組按組距、按大小標示於X軸,將次數標示於Y軸,各組資料以長方形的長條表示,其組距為長方形的寬度,次數為長方形的高度,各組的長方形條必須緊貼其前後組別的長方形條。 直方圖可展現資料的次數分配形狀、資料的集中與分布狀態。 2-*
30
LO2-4 Histogram Using Excel 2-*
31
次數多邊圖 Frequency Polygon
LO2-4 次數多邊圖 Frequency Polygon A frequency polygon, 與直方圖一樣能展現分配的形狀 (similar to a histogram, also shows the shape of a distribution.) 它乃是將各組的(組中點,次數)各點連結成多邊形線條 (It consists of line segments connecting the class midpoints of the class frequencies.) 2-*
32
Histogram versus Frequency Polygon
LO2-4 Histogram versus Frequency Polygon Both provide a quick picture of the main characteristics of the data (highs, lows, points of concentration, etc.) Advantage of the histogram: It depicts each class as a rectangle, with the height of the rectangular bar representing the number in each class. Advantage of the frequency polygon: It allows us to compare directly two or more frequency distributions. . 2-*
33
第35題 (p.44):統計考試成績直方圖
34
Ex 2-4 (p.36) 某特定族群的電子產品供應商的年進口值列於下表:
35
Ex 2-4 (p.36) 請繪製直方圖 請繪製相對次數多邊圖 請描述此分配的重要特點
36
累積次數分配Cumulative Frequency Distribution
LO2-4 累積次數分配Cumulative Frequency Distribution . 2-*
37
累積次數分配Cumulative Frequency Distribution
LO2-4 累積次數分配Cumulative Frequency Distribution 2-*
38
Ex 2-5 (p.40) 在喬治亞州 Brunswick 的 Home Depot 工作的15名員工的時薪整理成下表:
39
Ex 2-5 (p.40) 這個表格又稱作什麼? 請做出累積次數分配表,並繪製累積次數多邊形。
根據累積次數多邊形,有多少員工時薪不到$11?
40
第20題(p.40):房價的累積次數多邊形
41
第20題(p.40) a. 總共幾棟房屋? b. 組距=? c. 有100棟房屋的售價大約低於多少?
d. 75%的房屋售價低於多少(大概金額)? e. 大約有多少棟的房價介於 之間? f. 大約有多少棟的房價低於225?
Similar presentations